{"list":"other","total":80,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1708.08611","title":"Safe Reinforcement Learning via Shielding","created":"2017-08-29","cited_by_count":449},{"id":"1903.08792","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","created":"2019-03-21","cited_by_count":289},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"id":"1705.01292","title":"A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems","created":"2017-05-03","cited_by_count":163},{"id":"2202.11762","title":"Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methods","created":"2022-02-23","cited_by_count":151},{"id":"1612.03471","title":"Reinforcement Learning With Temporal Logic Rewards","created":"2016-12-11","cited_by_count":117},{"id":"1909.05304","title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","created":"2019-09-11","cited_by_count":77},{"id":"1810.00950","title":"Omega-Regular Objectives in Model-Free Reinforcement Learning","created":"2018-09-26","cited_by_count":75},{"id":"1909.07299","title":"Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning","created":"2019-09-16","cited_by_count":75},{"id":"2004.07584","title":"Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions","created":"2020-04-16","cited_by_count":68},{"id":"1609.07409","title":"Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications","created":"2016-09-23","cited_by_count":67},{"id":"1704.04341","title":"Environment-Independent Task Specifications via GLTL","created":"2017-04-14","cited_by_count":67},{"id":"2002.07080","title":"The Probabilistic Model Checker Storm","created":"2020-02-17","cited_by_count":66},{"id":"2101.11196","title":"Safe Multi-Agent Reinforcement Learning via Shielding","created":"2021-01-27","cited_by_count":61},{"id":"2204.00755","title":"Safe Reinforcement Learning via Shielding under Partial Observability","created":"2022-04-02","cited_by_count":56},{"id":"2112.15422","title":"Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)","created":"2021-11-25","cited_by_count":55},{"id":"1404.7073","title":"Probably Approximately Correct MDP Learning and Control With Temporal Logic Constraints","created":"2014-04-28","cited_by_count":54},{"id":"1801.08099","title":"Logically-Constrained Reinforcement Learning","created":"2018-01-24","cited_by_count":51},{"id":"1409.5486","title":"A Learning Based Approach to Control Synthesis of Markov Decision Processes for Linear Temporal Logic Specifications","created":"2014-09-18","cited_by_count":49},{"id":"2009.12612","title":"Neurosymbolic Reinforcement Learning with Formally Verified Exploration","created":"2020-09-26","cited_by_count":49},{"id":"1501.02573","title":"Shield Synthesis: Runtime Enforcement for Reactive Systems","created":"2015-01-12","cited_by_count":42},{"id":"2303.03226","title":"Safe Reinforcement Learning via Probabilistic Logic Shields","created":"2023-03-06","cited_by_count":42},{"id":"1402.2967","title":"Verification of Markov Decision Processes using Learning Algorithms","created":"2014-02-10","cited_by_count":39},{"id":"1907.07273","title":"An Inductive Synthesis Framework for Verifiable Reinforcement Learning","created":"2019-07-16","cited_by_count":39},{"id":"2309.13528","title":"Iterative Reachability Estimation for Safe Reinforcement Learning","created":"2023-09-24","cited_by_count":37},{"id":"2007.01223","title":"Verifiably Safe Exploration for End-to-End Reinforcement Learning","created":"2020-07-02","cited_by_count":34},{"id":"1510.05880","title":"Safety-Constrained Reinforcement Learning for MDPs","created":"2015-10-20","cited_by_count":33},{"id":"2210.03137","title":"Deep Inventory Management","created":"2022-10-06","cited_by_count":23},{"id":"2001.09467","title":"Tractable Reinforcement Learning of Signal Temporal Logic Objectives","created":"2020-01-26","cited_by_count":22},{"id":"2010.06797","title":"Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction","created":"2020-10-14","cited_by_count":22},{"id":"2212.01861","title":"Online Shielding for Reinforcement Learning","created":"2022-12-04","cited_by_count":22},{"id":"2209.07133","title":"COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model Checking","created":"2022-09-15","cited_by_count":19},{"id":"2011.04950","title":"Model-based Reinforcement Learning from Signal Temporal Logic Specifications","created":"2020-11-10","cited_by_count":18},{"id":"2305.01381","title":"Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees","created":"2023-05-02","cited_by_count":18},{"id":"1504.04662","title":"Permissive Controller Synthesis for Probabilistic Systems","created":"2015-04-18","cited_by_count":17},{"id":"1902.05632","title":"Verifiably Safe Off-Model Reinforcement Learning","created":"2019-02-14","cited_by_count":16},{"id":"2205.15827","title":"Robust Anytime Learning of Markov Decision Processes","created":"2022-05-31","cited_by_count":16},{"id":"2301.01526","title":"Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractions","created":"2023-01-04","cited_by_count":16},{"id":"2407.09645","title":"Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey","created":"2024-07-12","cited_by_count":16},{"id":"2005.07073","title":"Probabilistic Guarantees for Safe Deep Reinforcement Learning","created":"2020-05-14","cited_by_count":15},{"id":"2101.07202","title":"dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts","created":"2021-01-15","cited_by_count":14},{"id":"2305.17115","title":"Policy Synthesis and Reinforcement Learning for Discounted LTL","created":"2023-05-26","cited_by_count":14},{"id":"2410.12175","title":"Reinforcement Learning with LTL and $\\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards","created":"2024-10-16","cited_by_count":14},{"id":"2406.06507","title":"Verification-Guided Shielding for Deep Reinforcement Learning","created":"2024-06-10","cited_by_count":13},{"id":"2004.00273","title":"Statistically Model Checking PCTL Specifications on Markov Decision Processes via Reinforcement Learning","created":"2020-04-01","cited_by_count":12},{"id":"2301.04939","title":"Safe Policy Improvement for POMDPs via Finite-State Controllers","created":"2023-01-12","cited_by_count":12},{"id":"2210.01801","title":"Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation","created":"2022-10-02","cited_by_count":11},{"id":"2304.06281","title":"Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning","created":"2023-04-13","cited_by_count":11},{"id":"2308.02594","title":"SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents","created":"2023-08-03","cited_by_count":10},{"id":"1906.10640","title":"SOS: Safe, Optimal and Small Strategies for Hybrid Markov Decision Processes","created":"2019-06-25","cited_by_count":9},{"id":"2110.03184","title":"Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model","created":"2021-10-07","cited_by_count":9},{"id":"2305.07958","title":"More for Less: Safe Policy Improvement With Stronger Performance Guarantees","created":"2023-05-13","cited_by_count":9},{"id":"2409.10218","title":"Safety-Oriented Pruning and Interpretation of Reinforcement Learning Policies","created":"2024-09-16","cited_by_count":9},{"id":"2010.10618","title":"Runtime Safety Assurance Using Reinforcement Learning","created":"2020-10-20","cited_by_count":8},{"id":"2308.14424","title":"Shielded Reinforcement Learning for Hybrid Systems","created":"2023-08-28","cited_by_count":8},{"id":"2410.10460","title":"Compositional Shielding and Reinforcement Learning for Multi-Agent Systems","created":"2024-10-14","cited_by_count":8},{"id":"2011.15122","title":"Deep Controlled Learning for Inventory Control","created":"2020-11-30","cited_by_count":7},{"id":"2405.15994","title":"Verified Safe Reinforcement Learning for Neural Network Dynamic Models","created":"2024-05-25","cited_by_count":7},{"id":"2507.22040","title":"Structure-Informed Deep Reinforcement Learning for Inventory Management","created":"2025-07-29","cited_by_count":7},{"id":"2201.03698","title":"Verified Probabilistic Policies for Deep Reinforcement Learning","created":"2022-01-10","cited_by_count":6},{"id":"2409.10188","title":"Enhancing RL Safety with Counterfactual LLM Reasoning","created":"2024-09-16","cited_by_count":6},{"id":"2410.02817","title":"Neural Coordination and Capacity Control for Inventory Management","created":"2024-09-24","cited_by_count":6},{"id":"1906.08178","title":"Strategy Representation by Decision Trees with Linear Classifiers","created":"2019-06-19","cited_by_count":5},{"id":"2212.05337","title":"Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking","created":"2022-12-10","cited_by_count":5},{"id":"2410.18293","title":"1-2-3-Go! Policy Synthesis for Parameterized Markov Decision Processes via Decision-Tree Learning and Generalization","created":"2024-10-23","cited_by_count":5},{"id":"2001.05977","title":"Reward Shaping for Reinforcement Learning with Omega-Regular Objectives","created":"2020-01-16","cited_by_count":4},{"id":"2303.10382","title":"Interpretable Reinforcement Learning via Neural Additive Models for Inventory Management","created":"2023-03-18","cited_by_count":4},{"id":"2106.06931","title":"Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning","created":"2021-06-13","cited_by_count":3},{"id":"2109.06523","title":"Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking","created":"2021-09-14","cited_by_count":3},{"id":"2205.15455","title":"A Simulation Environment and Reinforcement Learning Method for Waste Reduction","created":"2022-05-30","cited_by_count":3},{"id":"2501.03187","title":"Turn-based Multi-Agent Reinforcement Learning Model Checking","created":"2025-01-06","cited_by_count":3},{"id":"2602.14505","title":"Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC","created":"2026-02-16","cited_by_count":3},{"id":"2303.10672","title":"Going faster to see further: GPU-accelerated value iteration and simulation for perishable inventory control using JAX","created":"2023-03-19","cited_by_count":2},{"id":"2307.09395","title":"Platelet Inventory Management with Approximate Dynamic Programming","created":"2023-07-18","cited_by_count":2},{"id":"2311.09811","title":"Runtime Verification of Learning Properties for Reinforcement Learning Algorithms","created":"2023-11-16","cited_by_count":2},{"id":"2411.14939","title":"Many happy returns: machine learning to support platelet issuing and waste reduction in hospital blood banks","created":"2024-11-22","cited_by_count":2},{"id":"2504.12023","title":"Evolutionary Reinforcement Learning for Interpretable Decision-Making in Supply Chain Management","created":"2025-04-16","cited_by_count":1}],"next_cursor":null}